Image de couverture de livre

Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gao, Jiaxuan, Guo, Yongjian, Guan, Zhong, Huang, Wen, Ma, Wanlun, Xiao, Xi, Xiong, Junwu, Wen, Sheng
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways
par: Deng, Zehang, et autres
Publié: (2024)

RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training
par: Sun, Haoran, et autres
Publié: (2026)

NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models
par: Huang, Wen, et autres
Publié: (2026)

MCPXKIT: The Unified Toolkit for Analyzing Model Context Protocol Security
par: Guo, Yongjian, et autres
Publié: (2025)

AdaptiveLoad: Towards Efficient Video Diffusion Transformer Training
par: Guo, Yucheng, et autres
Publié: (2026)

D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action Models
par: Guo, Yucheng, et autres
Publié: (2026)

WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
par: Jiang, Zhennan, et autres
Publié: (2026)

World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
par: Xiao, Junjin, et autres
Publié: (2025)

AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models
par: Sun, Xiaoquan, et autres
Publié: (2026)

Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction
par: Guan, Zhong, et autres
Publié: (2026)

StyleFool: Fooling Video Classification Systems via Style Transfer
par: Cao, Yuxin, et autres
Publié: (2022)

ZSVC: Zero-shot Style Voice Conversion with Disentangled Latent Diffusion Models and Adversarial Training
par: Zhu, Xinfa, et autres
Publié: (2025)

World2Act: Latent Action Post-Training from World Model Dynamics
par: Vuong, An Dinh, et autres
Publié: (2026)

RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models
par: Zhang, Hongyin, et autres
Publié: (2025)

Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends
par: Xiang, Tian-Yu, et autres
Publié: (2025)

IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model
par: Jiang, Anqing, et autres
Publié: (2025)

SarcasmMiner: A Dual-Track Post-Training Framework for Robust Audio-Visual Sarcasm Reasoning
par: Li, Zhu, et autres
Publié: (2026)

World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy
par: Liu, Xiaokang, et autres
Publié: (2026)

Gain or Pain: The Double‐Edged Sword Effect of Artificial Intelligence Adoption on Employee Service Performance
par: Jing Quan, et autres
Publié: (2025)

Stabilizing Recurrent Dynamics for Test-Time Scalable Latent Reasoning in Looped Language Models
par: Yang, Xiao-Wen, et autres
Publié: (2026)

Learning from Mistakes: Post-Training for Driving VLA with Takeover Data
par: Gao, Yinfeng, et autres
Publié: (2026)

Robust Predictions with Ambiguous Time Delays: A Bootstrap Strategy
par: Wang, Jiajie, et autres
Publié: (2024)

Capabilities and Fundamental Limits of Latent Chain-of-Thought
par: Zou, Jiaxuan, et autres
Publié: (2026)

Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies
par: Zhao, Guangyu, et autres
Publié: (2024)

Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training
par: Huang, Suning, et autres
Publié: (2026)

EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
par: Yang, Yantai, et autres
Publié: (2025)

StyleVLA: Driving Style-Aware Vision Language Action Model for Autonomous Driving
par: Gao, Yuan, et autres
Publié: (2026)

LDGuid: A Framework for Robust Change Detection via Latent Difference Guidance
par: Zhao, Jiaxuan, et autres
Publié: (2026)

VLA Model Post-Training via Action-Chunked PPO and Self Behavior Cloning
par: Wang, Si-Cheng, et autres
Publié: (2025)

Training Dynamics Impact Post-Training Quantization Robustness
par: Catalan-Tatjer, Albert, et autres
Publié: (2025)

Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variations
par: Liu, Hanqing, et autres
Publié: (2025)

VLA-RAIL: A Real-Time Asynchronous Inference Linker for VLA Models and Robots
par: Zhao, Yongsheng, et autres
Publié: (2025)

Interactive World Simulator for Robot Policy Training and Evaluation
par: Wang, Yixuan, et autres
Publié: (2026)

Learning Latent Dynamic Robust Representations for World Models
par: Sun, Ruixiang, et autres
Publié: (2024)

VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
par: Sun, Jingwen, et autres
Publié: (2026)

Kinematics-Aware Latent World Models for Data-Efficient Autonomous Driving
par: Li, Jiazhuo, et autres
Publié: (2026)

Adversarial Latent-State Training for Robust Policies in Partially Observable Domains
par: Ahuja, Angad Singh
Publié: (2026)

Surface Ligands in Nanocrystal Electrocatalysis: A Double‐Edged Sword
par: Hongyuan Sheng, et autres
Publié: (2025)

PointVLA: Injecting the 3D World into Vision-Language-Action Models
par: Li, Chengmeng, et autres
Publié: (2025)

DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving
par: jia, Feiyang, et autres
Publié: (2026)